Closed

Intel vs AMD: The Why

Introduction
The first thing you're thinking is that this is another "Intel is better than AMD" or "AMD is better than Intel" thread. Well, thank god it's not! I have a number of curiosities about the differences between Intel and AMD that I would love to have satisfied (as I'm sure many others do as well). I'm not sure where to begin, so we'll just jump right on in and hope for the best.

Notes before we begin...
Please don't post anything along the lines of "Intel is better because it is not AMD" or any cr*p like that. I'm looking for intelligible responses and factual/proven information.

Which is for who?
A lot of times I have seen AMD CPUs recommended to people who do things like Adobe and the like and Intel recommended to gamers (of course AMD is recommended to gamers too). I'm curious as to the reasoning behind these suggestions to PC builders. Can anyone link to some (recent) tests proving which is better in which case?

Intel is stronger. Why?
Now I know AMD users reading this section are already screaming out in outrage that I could say such a horrible thing; however, it's been proven with hundreds of thousands of hours worth of testing and benchmarking that Intel CPUs are more powerful than AMD CPUs (at least in gaming). Why is it that an the i7-3770K outperforms the FX-8350? Based just on the specs, the 8350 should be much more powerful than the 3770k; it has more cores and a much higher clock. Why, then, does the 3770k outperform the 8350? Does Intel use better materials? Do they place components in a more efficient way inside the CPU?

Benchmarks
-----
Source: Passmarks
3770K= 9,639
8350= 9,163
Difference= 476
-----
Source: CPUBOSS
Cinebench (all cores)
3770K= 25,703
8350= 32,437
Cinebench (single core)
3770K= 6,862
8350= 4,319
3D Mark 11
3770K= 8,470
8350= 6,980
134 answers Last reply
More about intel amd
  1. Intel and AMD use completely different architectures. You cannot compare specs with other architectures, it doesn't work that way.
  2. i7 3770k is ahead of fx 8350 because strong single core performance of intel.this is the main reason why intel is ahead
  3. e56imfg said:
    Intel and AMD use completely different architectures. You cannot compare specs with other architectures, it doesn't work that way.


    If that's true, why even bother with PassMark scores and the like?
  4. see here advanges you will undertand a bit

    - http://cpuboss.com/cpus/Intel-Core-i7-3770K-vs-AMD-FX-8350
  5. SlitWeaver said:
    e56imfg said:
    Intel and AMD use completely different architectures. You cannot compare specs with other architectures, it doesn't work that way.


    If that's true, why even bother with PassMark scores and the like?


    Cinebench score is more imp than passmark
  6. ASHISH65 said:
    see here advanges you will undertand a bit

    - http://cpuboss.com/cpus/Intel-Core-i7-3770K-vs-AMD-FX-8350

    This shows that the 3730K is more powerful, but not WHY. Good link nonetheless!

    ASHISH65 said:
    SlitWeaver said:
    e56imfg said:
    Intel and AMD use completely different architectures. You cannot compare specs with other architectures, it doesn't work that way.


    If that's true, why even bother with PassMark scores and the like?


    Cinebench score is more imp than passmark


    Cinebench, eh? Updating OP.
  7. actually passmark is a joke it is not proper way for comparision.i even say forget those cinebench,geek bench lol

    see benches which shows real world performance as it is better than those numbers and synthetic benches.

    - http://www.anandtech.com/bench/Product/551?vs=697

    - http://www.tomshardware.com/reviews/fx-8350-core-i7-3770k-gaming-bottleneck,3407.html
  8. ASHISH65 said:
    actually passmark is a joke it is not proper way for comparision.i even say forget those cinebench,geek bench lol

    see benches which shows real world performance as it is better than those numbers and synthetic benches.

    - http://www.anandtech.com/bench/Product/551?vs=697

    - http://www.tomshardware.com/reviews/fx-8350-core-i7-3770k-gaming-bottleneck,3407.html


    I'll keep this in mind, but it still only shows that the Intel CPU is better, but not why.
  9. Intel usually wins due to the better ipc (instruction per cycle)/better per core performance.
  10. there might be other reasons for that you may have to go in deep knowledge regarding their cpus
  11. ASHISH65 said:
    there might be other reasons for that you may have to go in deep knowledge regarding their cpus


    Do you have said deep knowledge? :D Because even if it's way above my level, I can do some research and bring a high level explanation to something at least semi-understandable to me.
  12. SlitWeaver said:
    e56imfg said:
    Intel and AMD use completely different architectures. You cannot compare specs with other architectures, it doesn't work that way.


    If that's true, why even bother with PassMark scores and the like?

    You can compare performance to each other but not specs. As I said, different architectures.
  13. SlitWeaver said:
    ASHISH65 said:
    there might be other reasons for that you may have to go in deep knowledge regarding their cpus


    Do you have said deep knowledge? :D Because even if it's way above my level, I can do some research and bring a high level explanation to something at least semi-understandable to me.


    http://en.wikipedia.org/wiki/Central_processing_unit

    Read up. Anything you want to know will be in there, or linked to in there.
  14. Cinebench is made using ICC, so Intel will always have a higher cinebench score unless an AMD chip is operating 200% faster than the intel chip because of the "not intel flag".

    Impressively...the FX8350 still score 6.9 where the i5-3570k is only 7.25(? iirc, anyway)...and the i7-3770k is only 7.5-7.75 or so...

    Also, here are some excerpts from a conversation that was had in another thread, and I am too lazy to retype it all:

    Quote:
    What he is talking about, are protocols...

    A software setup with data fed in a mostly serial manner favors intel, because intel's instruction execution protocol for their CPUs are 90% serial data...which means intel chips break down a serial stream of data faster (single threaded performance). AMD's instruction execution protocol for their CPUs are setup to run parallel streams of data (heavily threaded performance), which most software out right now is not designed to feed data to the CPU in this manner. So, data being fed serially to a CPU designed to run parallel streams of executions is inefficient, and favors one designed for that type of data streaming.

    For example...

    Picture you're at Wal-Mart (or where ever), and there are 8 checkout lanes open...the first lane has a line a mile long, and they will only allow 4 of the other 7 lanes to have a line 1 person long. It doesn't make any sense right? For starters, they're not even using all of the lanes available, and the ones they are, aren't being utilized efficiently.

    That's what's happening inside an AMD architecture FX8350 with current software...

    With Intel chips right now...it's more like the line at best buy...where you have 1 line a mile long, but the front person has 4 different cashiers to go to when they arrive at the front of the line.

    So, having 1 line a mile long doesn't slow them down, they're designed that way...

    However, once information is fed in a parallel manner to the CPU...AMD will have all 8 lanes at Wal-Mart open for business and the lines will be distributed equally with people (instructions for the CPU), but Intel will still have the Best buy type line with 4 people running a cash register...except that now there will be 4 or even 8 lines forming into that one line, which makes things slow down because they are not designed to execute like that.

    I hope the analogy makes this very complicated architecture discussion make sense.


    Quote:
    That's a great question man...

    Think of it like this, when you're multitasking, RAM has an effect on the amount of multitasking you can do, though windows negates this to some degree by putting "page file" on your HDD that is dynamic in size. What that means is that windows opens a file similar to RAM and loads files from it when you don't have enough RAM to load everything into RAM at once. RAM is faster, but your performance loss is only noticeable if you're running something extremely CPU/GPU heavy...like a game in 1440p or hardcore video encoding/rendering.

    When you're multitasking, AMD protocols allow your background programs to form a serial line in front of an unused core...so that you're not tapping the resources your foreground program is using.

    Now, say you were running 5 fairly intensive things at once...(let's say, streaming web videos, downloading multiple music files, and playing a web game...) Your i5-3570k would be able to execute 2-3 of those (depending on their resource needs) well...the others would be passed off to a virtual core in the background and would run at a considerably slower rate.

    Doing the same thing on an AMD 8 core chip, since only 1 of those requires any FP calculations, you could literally tap 5 cores to do all the work simultaneously.


    Quote:
    That's what hyperthreading is, it is essentially passing off background or foreground applications to a "virtual core" which the processor is basically taking a fraction of clock time each cycle to run the threads dedicated to the virtual core. Now, for the sake of hardware, the i5 doesn't have any "virtual cores" in intel speak...however, the 4 cores you have can divide clocktime by % to execute functions you're currently running(the definition of CPU multitasking effectively). This will tap resources you're using elsewhere, though it won't be a largely noticeable difference in your foreground application performance unless you're doing several CPU intensive things at once. So for example...your foreground application may be using 80% of 4 cores, and your background applications may be using 20% of the clocktime per cycle to run their functions, but it's at a highly reduced rate compared to what it would be if that was the primary program running.


    Also, intel is NOT faster than AMD, nor are their cores "stronger"...let me elaborate...to dispel this myth.

    Their architecture is used more efficiently...THAT is the difference. In reality...the AMD chip is easily 150% more raw horsepower than the intel chip...but programs, while they are getting there, do not currently fully utilize the architecture of the AMD...YET!

    Now, you should also know...places like teksyndicate, pureoverclock, overclock.net, openbenchmarking.org and other sites have a LOT of benchmarks where AMD wins...especially in games...

    As a matter of fact...Crysis 3, Far Cry 3, BF3, Metro 2033, Bioshock Infinite, and Tomb Raider all run as well on a 8350 OR in some cases better on the AMD. (Crysis 3 runs better on AMD, like it or not intel guys, it's proven)
  15. 8350rocks said:
    Cinebench is made using ICC, so Intel will always have a higher cinebench score unless an AMD chip is operating 200% faster than the intel chip because of the "not intel flag".

    Impressively...the FX8350 still score 6.9 where the i5-3570k is only 7.25(? iirc, anyway)...and the i7-3770k is only 7.5-7.75 or so...

    Also, here are some excerpts from a conversation that was had in another thread, and I am too lazy to retype it all:

    Quote:
    What he is talking about, are protocols...

    A software setup with data fed in a mostly serial manner favors intel, because intel's instruction execution protocol for their CPUs are 90% serial data...which means intel chips break down a serial stream of data faster (single threaded performance). AMD's instruction execution protocol for their CPUs are setup to run parallel streams of data (heavily threaded performance), which most software out right now is not designed to feed data to the CPU in this manner. So, data being fed serially to a CPU designed to run parallel streams of executions is inefficient, and favors one designed for that type of data streaming.

    For example...

    Picture you're at Wal-Mart (or where ever), and there are 8 checkout lanes open...the first lane has a line a mile long, and they will only allow 4 of the other 7 lanes to have a line 1 person long. It doesn't make any sense right? For starters, they're not even using all of the lanes available, and the ones they are, aren't being utilized efficiently.

    That's what's happening inside an AMD architecture FX8350 with current software...

    With Intel chips right now...it's more like the line at best buy...where you have 1 line a mile long, but the front person has 4 different cashiers to go to when they arrive at the front of the line.

    So, having 1 line a mile long doesn't slow them down, they're designed that way...

    However, once information is fed in a parallel manner to the CPU...AMD will have all 8 lanes at Wal-Mart open for business and the lines will be distributed equally with people (instructions for the CPU), but Intel will still have the Best buy type line with 4 people running a cash register...except that now there will be 4 or even 8 lines forming into that one line, which makes things slow down because they are not designed to execute like that.

    I hope the analogy makes this very complicated architecture discussion make sense.


    Quote:
    That's a great question man...

    Think of it like this, when you're multitasking, RAM has an effect on the amount of multitasking you can do, though windows negates this to some degree by putting "page file" on your HDD that is dynamic in size. What that means is that windows opens a file similar to RAM and loads files from it when you don't have enough RAM to load everything into RAM at once. RAM is faster, but your performance loss is only noticeable if you're running something extremely CPU/GPU heavy...like a game in 1440p or hardcore video encoding/rendering.

    When you're multitasking, AMD protocols allow your background programs to form a serial line in front of an unused core...so that you're not tapping the resources your foreground program is using.

    Now, say you were running 5 fairly intensive things at once...(let's say, streaming web videos, downloading multiple music files, and playing a web game...) Your i5-3570k would be able to execute 2-3 of those (depending on their resource needs) well...the others would be passed off to a virtual core in the background and would run at a considerably slower rate.

    Doing the same thing on an AMD 8 core chip, since only 1 of those requires any FP calculations, you could literally tap 5 cores to do all the work simultaneously.


    Quote:
    That's what hyperthreading is, it is essentially passing off background or foreground applications to a "virtual core" which the processor is basically taking a fraction of clock time each cycle to run the threads dedicated to the virtual core. Now, for the sake of hardware, the i5 doesn't have any "virtual cores" in intel speak...however, the 4 cores you have can divide clocktime by % to execute functions you're currently running(the definition of CPU multitasking effectively). This will tap resources you're using elsewhere, though it won't be a largely noticeable difference in your foreground application performance unless you're doing several CPU intensive things at once. So for example...your foreground application may be using 80% of 4 cores, and your background applications may be using 20% of the clocktime per cycle to run their functions, but it's at a highly reduced rate compared to what it would be if that was the primary program running.


    Also, intel is NOT faster than AMD, nor are their cores "stronger"...let me elaborate...to dispel this myth.

    Their architecture is used more efficiently...THAT is the difference. In reality...the AMD chip is easily 150% more raw horsepower than the intel chip...but programs, while they are getting there, do not currently fully utilize the architecture of the AMD...YET!

    Now, you should also know...places like teksyndicate, pureoverclock, overclock.net, openbenchmarking.org and other sites have a LOT of benchmarks where AMD wins...especially in games...

    As a matter of fact...Crysis 3, Far Cry 3, BF3, Metro 2033, Bioshock Infinite, and Tomb Raider all run as well on a 8350 OR in some cases better on the AMD. (Crysis 3 runs better on AMD, like it or not intel guys, it's proven)

    First off, love your name ahaha! Second, thanks for all the quoted information! :D Third, could you link me to some of the AMD dominating Intel examples? I never really see any of those (maybe Intel pays Google to hide them? ;) )
  16. To make the story short.

    Intel CPU: More on office productivity, workstation, media, grafix proccesing, gaming, etc
    AMD CPU: I can only think of gaming, what else? maybe file compression? :D

    Intel: Withstand higher temperature. Proven and tested since their older generations
    AMD: Can withstand, but not that much.

    Direct to the point: Intel DOMINATES the AmD. Simple as that!
  17. If all modern software was programmed perfectly to take full advantage of all resources available, and utilized each core equally, AMD cpus would probably beat Intel on everything. With the large variety of software out there, single core performance remains important to chug through ineffecient programming. This is partly why Intel excels at certain games (like Skyrim), because they are only programmed to take advantage of 1 or 2 cores, which favors an Intel advantage. Even if you are dealing with video/photo programs like Photoshop or After Effects, you are likely going to be using filters or 3rd party plugins that are not programmed efficiently and will lolly-gag on one core (and not even use 100% of that one core). I decided to go with a 2600k to hedge bets against those ineffecient single core programs and badly ported games, and still have some hyper-threading for efficiently programmed rendering and encoding. But if you want a reason for Intel's advantage over AMD, it's partly the deficiency of software developers to take advantage of more cores. There's also legacy software people haven't upgraded yet, mobile CPUs that are still on one core... the multi-core revolution we were all waiting for, and AMD bet on, hasn't quite come to a boil yet.
  18. PapaCrazy said:
    mobile CPUs that are still on one core...


    The rest of your speech was fine, but this stuck out. My phone is dual-core, some are 4-core, and the Exynos 8-core has two 4-core CPU clusters. All in one phone.
  19. IPC?


    This post makes me cry.
  20. SlitWeaver said:
    PapaCrazy said:
    mobile CPUs that are still on one core...


    The rest of your speech was fine, but this stuck out. My phone is dual-core, some are 4-core, and the Exynos 8-core has two 4-core CPU clusters. All in one phone.


    I focus my resources into desktops not mobile devices, but if they're doing multi-core on phones that's cool I guess. Makes me wonder how many mobile apps are actually programmed for multi-core, but its interesting nonetheless.
  21. Not many I would presume. Given that mobile ARM quad cores are relatively new and make up a small sector of the mobile market.

    Even the the PC market that has had quad-cores being relatively cheaply and available since 2008-2009 still have applications like iTunes that aren't optimised for quad-core.
  22. PapaCrazy said:
    SlitWeaver said:
    PapaCrazy said:
    mobile CPUs that are still on one core...


    The rest of your speech was fine, but this stuck out. My phone is dual-core, some are 4-core, and the Exynos 8-core has two 4-core CPU clusters. All in one phone.


    I focus my resources into desktops not mobile devices, but if they're doing multi-core on phones that's cool I guess. Makes me wonder how many mobile apps are actually programmed for multi-core, but its interesting nonetheless.


    Pretty sure all [smart]phones are multi-core now. I don't use my phone for anything more than web-browsing, emailing, text messaging, and other basic things like that. Use it to test my apps, but those are hardly resource intensive. Why are phones multi-core? I don't know, just know that they are :)
  23. Because you can't continue scaling frequency. Other methods had to be found to increase performance.

    There's that and marketing comes into it as well.

    "I have quad core! No I have Hex core... Haha I beat you both with an Octo core"

    Etc. Etc.
  24. amdfangirl said:
    Because you can't continue scaling frequency. Other methods had to be found to increase performance.

    There's that and marketing comes into it as well.

    "I have quad core! No I have Hex core... Haha I beat you both with an Octo core"

    Etc. Etc.

    I bought that 37.6ghz i7, guess I win? :na:
  25. Arguing things on forums has taught me to ignore people who insist they have a 37.6Ghz Core i7.
  26. amdfangirl said:
    Because you can't continue scaling frequency. Other methods had to be found to increase performance.


    Because I need my phone to have an i7-3770K in it ahaha...funny though, they make tablets with i7s in them...
  27. They are mostly rebranded desktop Core i3s that run with a lower clockspeed/voltage.
  28. Funny that there's phones out there now with more cores than I have in my PC... that's kind of humiliating, actually. Damn smart phones.
  29. See, it's not that bad.

    It's like PCs have mathematics professors whilst mobile phones have high school grads.

    If you have the same number of maths professors and high school grads - you might have the same number of mathematicians, but it is clear which would be superior.
  30. PapaCrazy said:
    Funny that there's phones out there now with more cores than I have in my PC... that's kind of humiliating, actually. Damn smart phones.


    :lol:
  31. amdfangirl said:
    See, it's not that bad.

    It's like PCs have mathematics professors whilst mobile phones have high school grads.

    If you have the same number of maths professors and high school grads - you might have the same number of mathematicians, but it is clear which would be superior.


    hah! awesome analogy. I can imagine the HS grads getting confused and giving up on certain problems... as has been my experience with phones.
  32. amdfangirl said:
    See, it's not that bad.
    It's like PCs have mathematics professors whilst mobile phones have high school grads.
    If you have the same number of maths professors and high school grads - you might have the same number of mathematicians, but it is clear which would be superior.


    Watch out!
    All professors were once high school grads.
    LoL
  33. Correct me if I am wrong.. But as I understand with my consumer level knowledge, the architecture efficiency may work in the following way.

    Consider two elementary students A and B.
    "A" can do 5 calculations in a second, "B" can do 3 calculations per second. Thus "A" has a frequency of 5Hz, "B" has 3Hz.
    "A" solves the problem 2+2+2 =? as "2+2=4, and 4+2=6". That is 2 separate steps of calculations. So to solve five such problems "A" will take 2 seconds (10 calculations, 2 for each problem)

    While "B" has learnt multiplication and can do the same problem in one single step of calculation "3*2=6" and thus in 2 seconds he can solve 6 such problems. Thus a 3Hz brain can solve more problems than a 5Hz brain. And a 3.5GHz cpu can perform faster than a 4GHz processor.

    But. when does "A" get the edge? If a problem like 2+3+5 comes. B CANNOT convert this to a multiplication problem and has to do 2 steps of addition and thus will fall behind "A" who is faster in addition problems. Similarly Intel can perform faster in tasks optimized for its architecture but sometimes lags behind AMD in tasks which are not optimized for it but requires brute force (more calculations per second) where more GHz matters.

    Simply put, this should explain you WHY. I am not a Computer science guy and therefore am not aware of the microprocessor science and CPU architecture, but with my limited understanding I believe the above analogy.
    Any suggestions, corrections are welcome.

    And someone please tell me if I am correct. I will give myself a treat and offer a toast for you.
    Cheers....
  34. Far Cry 3, Crysis 3, Metro 2033 @ 1080p and 1440p Reviews:

    http://teksyndicate.com/videos/amd-fx-8350-vs-intel-3570k-vs-3770k-vs-3820-gaming-and-xsplit-streaming-benchmarks

    There's a gaming benchmark, on my way out the door, will add you some more links later.
  35. 8350rocks said:
    Far Cry 3, Crysis 3, Metro 2033 @ 1080p and 1440p Reviews:

    http://teksyndicate.com/videos/amd-fx-8350-vs-intel-3570k-vs-3770k-vs-3820-gaming-and-xsplit-streaming-benchmarks

    There's a gaming benchmark, on my way out the door, will add you some more links later.


    Thanks! So it would appear you'd need to select which CPU based on which games you're going to play; AMD some Intel others. Can't wait to see what other videos and benchmarks you link :D One thing I kniw though, my friend has the 8350 and it overheats pretty bad with the stock cooler. Also, more power consumption because of larger die :P
  36. 8350rocks said:
    Far Cry 3, Crysis 3, Metro 2033 @ 1080p and 1440p Reviews:

    http://teksyndicate.com/videos/amd-fx-8350-vs-intel-3570k-vs-3770k-vs-3820-gaming-and-xsplit-streaming-benchmarks

    There's a gaming benchmark, on my way out the door, will add you some more links later.


    that is the most retarded review site i have ever seen.
  37. SlitWeaver said:
    8350rocks said:
    Far Cry 3, Crysis 3, Metro 2033 @ 1080p and 1440p Reviews:

    http://teksyndicate.com/videos/amd-fx-8350-vs-intel-3570k-vs-3770k-vs-3820-gaming-and-xsplit-streaming-benchmarks

    There's a gaming benchmark, on my way out the door, will add you some more links later.


    Thanks! So it would appear you'd need to select which CPU based on which games you're going to play; AMD some Intel others. Can't wait to see what other videos and benchmarks you link :D One thing I kniw though, my friend has the 8350 and it overheats pretty bad with the stock cooler. Also, more power consumption because of larger die :P



    Yes, stock cooler is garbage...get a 212 EVO

    http://www.overclock.net/t/1333027/amd-fx-8350-vs-i5-3570k-delidded-single-gpu-and-crossfire-gpu

    That link shows some benches using FX8350 @ 4.8 GHz vs i5-3570k @ 4.8 GHz.

    8350 wins 3 benches intel wins 3 benches.

    @iam2thecrowe:

    His method is sound and his tests are accurate...what else do you want from a benchmark? Someone who spews BS about Intel > AMD no matter the result?
  38. iam2thecrowe said:
    8350rocks said:
    Far Cry 3, Crysis 3, Metro 2033 @ 1080p and 1440p Reviews:

    http://teksyndicate.com/videos/amd-fx-8350-vs-intel-3570k-vs-3770k-vs-3820-gaming-and-xsplit-streaming-benchmarks

    There's a gaming benchmark, on my way out the door, will add you some more links later.


    that is the most retarded review site i have ever seen.


    Um.

    No.

    It's the best review site out there! Look at how they list out the data and everything, makes anandtech, tom's, and everybody else look stupid.
  39. I detect sarcasm, if you want a pretty spreadsheet and graph, he posted it in the comments on page 2. The test was run with a GTX 670 a few weeks later and the results were similar.

    https://docs.google.com/spreadsheet/ccc?key=0AgHEgqqaasTkdGJmNmpNMGowa0hqX3VUNS1ZZEpaUlE

    In case anyone was too lazy to fish for the more "professional" looking results.
  40. SlitWeaver said:
    Introduction
    The first thing you're thinking is that this is another "Intel is better than AMD" or "AMD is better than Intel" thread. Well, thank god it's not! I have a number of curiosities about the differences between Intel and AMD that I would love to have satisfied (as I'm sure many others do as well). I'm not sure where to begin, so we'll just jump right on in and hope for the best.

    Notes before we begin...
    Please don't post anything along the lines of "Intel is better because it is not AMD" or any cr*p like that. I'm looking for intelligible responses and factual/proven information.

    Which is for who?
    A lot of times I have seen AMD CPUs recommended to people who do things like Adobe and the like and Intel recommended to gamers (of course AMD is recommended to gamers too). I'm curious as to the reasoning behind these suggestions to PC builders. Can anyone link to some (recent) tests proving which is better in which case?

    Intel is stronger. Why?
    Now I know AMD users reading this section are already screaming out in outrage that I could say such a horrible thing; however, it's been proven with hundreds of thousands of hours worth of testing and benchmarking that Intel CPUs are more powerful than AMD CPUs (at least in gaming). Why is it that an the i7-3770K outperforms the FX-8350? Based just on the specs, the 8350 should be much more powerful than the 3770k; it has more cores and a much higher clock. Why, then, does the 3770k outperform the 8350? Does Intel use better materials? Do they place components in a more efficient way inside the CPU?

    Benchmarks
    -----
    Source: Passmarks
    3770K= 9,639
    8350= 9,163
    Difference= 476
    -----
    Source: CPUBOSS
    Cinebench (all cores)
    3770K= 25,703
    8350= 32,437
    Cinebench (single core)
    3770K= 6,862
    8350= 4,319
    3D Mark 11
    3770K= 8,470
    8350= 6,980


    1) AMD is good enough for gamers. If I was to simply to a minimum I would say that AMD FX is better for multitasking and modern parallel code, whereas Intel i7-3770k is better for older single threaded code.

    2) There are several benchmarks showing how the FX-8350 beats an i7-3770k.

    3) AMD chips are a victim of the Criple_AMD function found in Intel compilers which generate suboptimal code when detect a AMD chip. Cinebench is not optimized for AMD chips for instance.

    4) AMD FX-8350 holds the world-wide record of overclocking, showing the excellent design and materials used.

    5) PassMark scores are obtained from averaging users submissions. They do not compare chip to chip but an average-users-built to another average-users-built. Since the FX is a cheaper chip it is likely that most submission from FX owners are using cheaper parts (HDD, SDD, RAM, MOBO...) than Intel owners. Moreover, the difference in the score is of about a 5%, which is within the limits of error of the score.
  41. Don't bring Logan into this. His testing methodology is beyond questionable and so are his results. He doesn't know what he is doing so please do not include him into this argument.
  42. e56imfg said:
    Don't bring Logan into this. His testing methodology is beyond questionable and so are his results. He doesn't know what he is doing so please do not include him into this argument.

    No, he has the best testing methodology. I don't know what you're talking about! :na:
  43. e56imfg said:
    Don't bring Logan into this. His testing methodology is beyond questionable and so are his results. He doesn't know what he is doing so please do not include him into this argument.


    But if intel had won those benchmarks it would be ok to include them right? Because then intel would have won...and you would say..."Well, it goes along with all the intel biased sites I read so, why not?"

    Even Tom's shows the FX8350 is VERY close to the intel chips in MANY games...you can't argue over 3-5 FPS when the margin for error is 10% of 100-120 FPS...you're well below margin for error no matter how you slice it.

    So, please...stop with your "holier than thou" attitude about reviews that do not specifically favor intel.

    Can we have an intelligent discussion about merits and deficiencies without the intel crowd causing a raucous over the 2 being FAR closer in performance than they initially thought?
  44. Like you'll get anywhere with the username "8350rocks" :P

    Anyway, I have a feeling this thread is going to turn to a flamewar.
  45. 8350rocks said:
    e56imfg said:
    Don't bring Logan into this. His testing methodology is beyond questionable and so are his results. He doesn't know what he is doing so please do not include him into this argument.


    But if intel had won those benchmarks it would be ok to include them right? Because then intel would have won...and you would say..."Well, it goes along with all the intel biased sites I read so, why not?"

    Even Tom's shows the FX8350 is VERY close to the intel chips in MANY games...you can't argue over 3-5 FPS when the margin for error is 10% of 100-120 FPS...you're well below margin for error no matter how you slice it.

    So, please...stop with your "holier than thou" attitude about reviews that do not specifically favor intel.

    Can we have an intelligent discussion about merits and deficiencies without the intel crowd causing a raucous over the 2 being FAR closer in performance than they initially thought?

    No it's not about whoever is winning. His results are constantly inconsistent and there's no way in hell that the 8350 doubles the performance compared to the 3570K. Arma and Far Cry 3. I know the 8350 plays better with Far Cry 3 but everything on the web shows that the 3570K is only a few frames from the 8350. Give me some benchmarks that agree with Logan's ludicrous results. Unless Logan is the only one who is right and every other tech review site is wrong...

    Where in this thread say that I favor Intel? Both CPUs should've been consistently neck-to-neck in all benchmarks. Logan's results are all over the place. I'm bashing on Logan, not AMD.

    You can't have an intelligent argument with illogical proof. Give me one well known Intel biased site, I dare you.
  46. e56imfg said:
    8350rocks said:
    e56imfg said:
    Don't bring Logan into this. His testing methodology is beyond questionable and so are his results. He doesn't know what he is doing so please do not include him into this argument.


    But if intel had won those benchmarks it would be ok to include them right? Because then intel would have won...and you would say..."Well, it goes along with all the intel biased sites I read so, why not?"

    Even Tom's shows the FX8350 is VERY close to the intel chips in MANY games...you can't argue over 3-5 FPS when the margin for error is 10% of 100-120 FPS...you're well below margin for error no matter how you slice it.

    So, please...stop with your "holier than thou" attitude about reviews that do not specifically favor intel.

    Can we have an intelligent discussion about merits and deficiencies without the intel crowd causing a raucous over the 2 being FAR closer in performance than they initially thought?

    No it's not about whoever is winning. His results are constantly inconsistent and there's no way in hell that the 8350 doubles the performance compared to the 3570K. Arma and Far Cry 3. I know the 8350 plays better with Far Cry 3 but everything on the web shows that the 3570K is only a few frames from the 8350. Give me some benchmarks that agree with Logan's ludicrous results. Unless Logan is the only one who is right and every other tech review site is wrong...

    Where in this thread say that I favor Intel? Both CPUs should've been consistently neck-to-neck in all benchmarks. Logan's results are all over the place. I'm bashing on Logan, not AMD.

    You can't have an intelligent argument with illogical proof. Give me one well known Intel biased site, I dare you.


    Anandtech is intel biased...read their reviews...if you actually read the way they talk about AMD, you pick it up. They dismiss AMD like they were always going to be an "also ran" before it even started, and they downplay the strengths.

    Second, Far Cry 3, in his review was 3 FPS difference, Crysis 3 was the only game where a dramatic difference existed, Metro 2033 was a maximum difference of 5-7 FPS in the FX8350s favor.

    Where were those results skewed?

    When he ran it with the GTX 670 the FPS in Far Cry 3 was a difference of 2 FPS in favor of intel being ahead.

    Who is biased toward AMD now, or with poor scientific methods? Your results you cited were how close? A few FPS? Hmm...remarkably...they are similar! I wonder why that would be...?
  47. Sorry but Anandtech is not Intel biased. That's ludicrous.

    Logan didn't even bench Crysis 3... Did you even look at your own proof lol? Crysis 3 wasn't even released when he made these videos. I think you're referring to Warhead.
    http://www.youtube.com/watch?v=4et7kDGSRfc&feature=player_detailpage#t=443s
    http://www.youtube.com/watch?v=4et7kDGSRfc&feature=player_detailpage#t=433s

    I'm not saying all of his results are wrong but some are just laughable at best. I would be just as suspicious if he said the 3570K had double or triple the FPS against the 8350.

    I think someone should close this thread. This isn't even on topic.
  48. e56imfg said:
    Sorry but Anandtech is not Intel biased. That's ludicrous.


    I read many reviews from them and if it is not bias then it is plain ignorance plus lack of professionalism favouring certain brands.

    Moreover, what 8350rocks is saying is well-known to google search:

  49. AMD uses half core technology but they market the half cores as whole. So FX-8350 really just has the same amount as i7-3770k.

    Source:
    http://en.wikipedia.org/wiki/Ivy_Bridge_(microarchitecture)#Desktop_processors
    http://en.wikipedia.org/wiki/Piledriver_(microarchitecture)#Desktop
Ask a new question

Read More

Intel AMD CPUs